INDEX

Explanations

words related to academic or professional history and accomplishments

oai_token-act-pair · gemini-2.0-flash

career/experience

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.95

 typelib

-0.84

 متعلقه

-0.83

 kaarangay

-0.78

mybatisplus

-0.76

SourceChecksum

-0.72

invokeLater

-0.71

 disambiguazione

-0.71

 ویکی‌پدیا

-0.70

rungsseite

-0.68

POSITIVE LOGITS

DIS

0.45

UN

0.45

UN

0.43

梵

0.43

arg

0.43

gal

0.42

 İstanbul

0.41

MessageHandler

0.41

comp

0.41

US

0.41

Activations Density 5.238%

words related to academic or professional history and accomplishments

career/experience

No Comments

No Known Activations